Smart bikes: solving challenges for riders, cities and the planet

Smart bicycles are transforming the way we ride. They blend cutting-edge technology with human-powered mobility to tackle today’s needs: sustainability, fitness, safety and convenience. By embedding IoT, AI and real-time connectivity into the product innovation process, these bicycles become far more than a means of transport. They’re a rider’s partner in reaching health goals, navigating city streets and staying connected. Beyond the rider, smart bikes help cities reduce traffic congestion, improve air quality and support sustainable urban planning, all while contributing to a greener, healthier planet.

5 innovative features powering the smart bike for the day after tomorrow

Health integration transforms the rider’s ride into a fitness powerhouse. Built-in sensors in the handlebars or seat track your heart rate, oxygen levels, stress, cadence and calories burned. Paired with apps, the bike becomes a personal coach, giving real-time feedback and tailored advice. It creates custom workout plans based on personal goals, progress and data, offering challenges, intervals or recovery rides. Picture cycling to work at 30 km/h with a heart rate of 130 bpm, adaptive algorithms adjust the electric assist to keep you on track. A voice assistant might even guide you, reminding you to tweak your pace or posture for top performance. After your ride, your fitness app analyzes everything, offering tips on stretching, nutrition and recovery to help you train smarter and feel great.

Navigation and safety features make the smart bike a trusted travel companion. GPS and augmented reality displays guide the rider safely through city streets, while a heads-up display on the handlebars shows clear directions and route changes without creating distractions. Intelligent lights adjust brightness and direction to the current speed and surroundings, boosting visibility for both the rider and others. Proximity sensors and cameras will ensure awareness of nearby vehicles, pedestrians and obstacles, sending instant audio or vibration alerts to avoid accidents. It’s a smarter, safer way to commute, every ride.

Digital locking and anti-theft features make parking the smart bike worry-free. IoT-enabled locks let the rider secure and unlock the bike remotely using an app. If it’s stolen, GPS tracking pinpoints its location and can be shared with law enforcement for quick recovery. Sensors detect tampering, sending instant alerts to the phone connected and triggering a loud alarm to scare off thieves. Plus, a connected network of smart bikes notifies nearby riders if the stolen bicycle is spotted. Need to share the bike? Grant access through the app and track it in real-time. It’s the perfect mix of security, control and convenience.

Weather and traffic alerts keep the rider one step ahead on every ride. Real-time updates on weather, air quality and traffic conditions help select the safest, fastest and most comfortable route. With this feature, they’ll always know when to pack a raincoat, avoid congested areas or find a cleaner air path for a better commute.

Crash detection and emergency alerts have the rider’s back when it matters most. Smart sensors instantly tell the difference between a little bump and a serious fall. Apps automatically alert emergency contacts and first responders, so help gets there fast. Need extra support? A community SOS network connects the rider with nearby riders who can lend a hand. Plus, an AI assistant steps in to guide in fixing crash damage or even a flat tire. With these features, they’re always covered, no matter what the road throws their way.

Enhancing user interaction toward a tailored experience

Smart bikes offer a customizable experience by syncing with user profiles. Fitness enthusiasts can sync heart rate and performance data with wearables or favorite fitness apps. Urban commuters get seamless integration with communication preferences, like text-to-voice notifications during rides or muting distractions. Additionally, riders can even pre-set features like automatic light activation at dusk or routes optimized for their go-to destinations.

Innovation driving the smart bike revolution

The smart bicycle exemplifies how mobility and digital ecosystems can converge to create a healthier, safer and more efficient way of living. It’s more than just a smart choice, it’s a visionary leap into the future of cycling. As a prime example of how to innovate for the day after tomorrow, the smart bike demonstrates the power of integrating transformative features from the start of product innovation development. By thinking ahead, it becomes more than a vehicle; it’s a seamless extension of the rider’s connected world, paving the way for a revolutionary cycling experience.

The post Reinventing the smart bike: A glimpse into the evolution of mobility, health and lifestyle appeared first on Verhaert Masters in Innovation.

The post Reinventing the smart bike: A glimpse into the evolution of mobility, health and lifestyle appeared first on Verhaert Masters in Innovation.

Let’s dive into the diverse avenues of progress in the coffee industry!

1. Intelligent home roasting

Redefining coffee quality and sustainability

Bunafr‘s participation in CES 2024 introduces an intelligent home coffee roaster that transforms the roasting experience. Beyond being a machine, it offers a fully automated, smoke-free process with advanced technologies. The innovation focuses on personalized roasting, sustainability, and direct connections with coffee farmers, promising an unparalleled coffee experience.

Coffee machines: ©Bunafr (left) – ©Midea (right)

2. AI-guided personalization

The future of smart coffee systems

Midea presents the ‘Barista Brew’ coffee brewer/grinder system, a smart coffee solution that leverages AI-guided personalization. With one-touch favorites, BrewIQ AI suggestions and easy tracking, this innovation aims to make coffee brewing accessible to all, regardless of expertise. It sets a new standard for smart coffee systems, emphasizing simplicity and technological advancement.

3. Premium espresso with technological precision

Bosch’s fully automatic machines

Bosch introduces a new line of fully automatic espresso machines, emphasizing premium-quality coffee and technological precision. The Aroma Max System, Active Select Display, and integration with Home Connect® redefine the home coffee experience. This innovation aims to deliver consistent coffee quality, personalization and over 35 beverage options through advanced technology.

Coffee machines: ©FrazyBot (left) – ©Bosch (right)

4. Robotic beverage crafting

The FrazyBot revolution

FrazyBot, a modular beverage brewing robot, redefines at-home drink preparation. Designed to minimize manual interventions and clean-up, the FrazyBot promises precision and professionalism, comparable to café or bar drinks. The Ingredient-Sensing Robotic Technology (InSeRT) ensures an effortless, customizable and high-quality beverage experience at the press of a button.

5. Eco-friendly espresso

Lavazza’s Tiny Eco revolution

Lavazza‘s Tiny Eco emerges as a compact and sustainable espresso machine made from recycled plastic and compostable capsules. With a focus on sustainability and design, this innovation offers an authentic Italian espresso experience. Its easy maintenance, dishwasher-safe components and compatibility with Lavazza capsules contribute to an eco-friendly and responsible coffee-making approach.

Coffee machine ©Lavazza

Comparing the strategies behind the devices

How do these devices and innovation strategies compare to one another? We made the following assessment based on people’s opinions on a coffee lover’s user perception. We used criteria such as emotional evocation, premium feel, personalization, and the social responsibility of the device from a user’s perception.

Notes:

• Emotion addresses: Reflects how the innovation addresses the emotional aspect of the coffee lover.
• Premium feel: Represents the perceived luxury or premium feel associated with the innovation.
• More personalized feeling: Indicates the degree to which the innovation provides a personalized and tailored experience.
• Social responsibility: Reflects the level of commitment to social and environmental responsibility in the innovation.

People however don’t switch their current coffee maker easily, you need a new compelling reason. When looking for innovative features you need to investigate the importance and the satisfaction level of each of the features. That’s why we also added an assessment relative to the willingness to pay.

Notes:

• Satisfaction rating (1-5): Reflects the current satisfaction level with the existing coffee machine.
• Eagerness to Upgrade (1-5): Indicates how interested the potential buyer is in upgrading the coffee machine based on the discussed factors.
• Willingness to Pay Rating (Low-Med-High): Represents the potential buyer’s willingness to pay for an upgraded coffee machine, considering the perceived value of the innovations.

In conclusion

In conclusion, these innovations highlight diverse avenues of innovative progress for the coffee industry, ranging from intelligent roasting and AI-guided personalization to hands-free brewing and eco-friendly espresso solutions. Each emphasizes the unique innovation direction chosen by these respective brands, providing consumers with a glimpse into the transformative landscape of home coffee experiences. However, only 3 concepts stand out in giving enough reasons to switch from their older device to a new coffee maker. This brings me to my final thought: Would a device combining the 3 outstanding strategies (premiumized coffee, robotics and sustainability) be the holy grail of innovation? Or would it more likely fit in the contradiction of less is more?

The post As seen at CES: brewing the future of innovation in coffee experiences appeared first on Verhaert Masters in Innovation.

The post As seen at CES: brewing the future of innovation in coffee experiences appeared first on Verhaert Masters in Innovation.

Setting the SARWS weather scene

If you haven’t read our perspective on the SARWS project, here’s a short recap to set the scene: the SARWS project was set up to evaluate how car technologies can provide real-time weather data and proactive safety warnings for drivers. By equipping vehicles with various types of external sensors, we created a fleet of mobile local weather stations. Together with a fanless mini pc, these sensors formed the In Car Smart Sensor Node (ICSSN), capturing the raw data and then centralizing, (pre-)processing and aggregating it before distributing it further to the cloud. In this first testing stage, we focused on the more classical sensors, like temperature and humidity, but didn’t really include the camera yet. So, what did we do with the camera? We created a smart sensor with it called ‘WeathercAIm’.

WeathercAIm?

So, what is this WeathercAIm and what does it do? WeathercAIm is a smart sensor inside the vehicle that combines a camera, a sort of dashcam functioning as the eyes of the vehicle, connected to the mini pc, the brain, with edge artificial intelligence (AI) processing running on it.

It has AI in it? Surely you must be able to ask it questions about the current weather or generate some pretty weather pictures, right? Or maybe even generate the weather you desire? Wouldn’t that be cool?! With all the fuss, not to say hype, about generative AI, you might overlook the other types of AI. But, if you’re a loyal reader of our insights, you know that there are many more types of AI, which have already proven their merits in various industries and applications that are also very cool.

With WeathercAIm we didn’t want to generate, but “see” the actual current weather based on the pictures taken by the camera with AI. More precisely, for SARWS we wanted to recognize if there’s precipitation, which precipitation type (rain, snow, melting snow, hail), and visibility (fog). This is in principle a classification task.

Besides the main weather classification goal, we also had to manage constraints and requirements related to privacy, GDPR and data connection bandwidth and usage to a minimum. As you can imagine, sending tons of pictures into the cloud via a mobile connection would be quite a challenge. That’s why we choose to process the data locally on the edge, for example on the mini pc. This also influenced our choices and approach for the AI model, as can’t run the super big AI models on the edge as you can in the cloud.

Supervised learning approach for multiclass classification

Since we’re always in for a challenge, we tackled the in-principle multi-classification task problem with a single AI, machine learning (ML) classifier. For this, we decided to make a classifier with multiple classes, one for ‘no precipitation’, one for each of the precipitation types, and one for visibility.

Dry technical text road ahead, with possibly some slippery patches. Skip to the next paragraph if desired.
A supervised learning approach for multiclass classification was used for the ML model. We opted for a classifier based on a convolutional neural network (CNN), a deep learning approach, that had already proven its merits in the computer vision field. More precisely, we used a CNN with a ResNet50v2 backbone and a dense layer as the classification head. The CNN is trained via transfer learning with fine-tuning and the backbone network is pre-trained on ImageNet, and the CNN model is implemented in Keras/TensorFlow. If you want even more nitty-gritty details about the WeathercAIm (initial) model, make sure to check out this paper.

To train an ML model you need data. Unfortunately, for our first ML model, we didn’t have any pictures available from the vehicle fleet yet, as the limited data-gathering campaign would only be done later in the project. To already evaluate the feasibility of WeathercAIm for detecting the weather, an initial model was trained on the adverse weather dataset (AWD) public dataset. The initial model we trained seemed to perform quite well on the AWD dataset which indicated that the approach was feasible.

After the model is trained, we can use it to do actual weather classifications. A captured image is processed by the different layers of the CNN to come to a weather classification, as you can see in the GIF below. We already deployed this first initial model in production in the initially limited fleet for the field test and data gathering campaign.

Field test results

Initial results from the field test revealed that there were still some challenges and room for improvement in the accuracy on real-life production data. Some observations of the field test and data:

• The resolution of the camera doesn’t allow for high performance in changing lighting conditions, producing lesser quality images than the camera images from the AWD dataset.
• The environmental settings, ex. camera placement, urban scenes and weather conditions were different compared to the AWD dataset, which was taken in Canada.
• Actual data was very imbalanced, with ‘no precipitation’ being an extreme majority class (see the dataset distribution figure below). The class distribution was also quite different compared to AWD. In general, such highly-skewed datasets are very challenging to get good modeling and predictions.
• For some rarer weather types, like hail, there was only a marginal number of images captured, which makes it hard to model them. The real-life data also included special (non-weather) cases, like tunnels, vehicles in the garage, etc.
• The weather condition on the images was sometimes very difficult to judge, but also for humans, especially in case of the lesser quality of images. This also made labeling of camera images challenging and tedious.

SARWS field test camera dataset distribution

After the data gathering campaign part of the field test, the predictions of the initial model have been back-tested on the fully captured and labeled field dataset. This showed that, on contrary to the AWD dataset, it didn’t perform well and achieved a much lower accuracy. This confirmed the problem with the worse image quality images, difficult-to-judge weather types and class imbalance and the need to update and retrain the WeathercAIm model after the development phase on this new ground-truth data.

As for any ML project, good quality and representative data is crucial to train the ML model!

To improve WeathercAIm to suit the actual field production conditions, a more data-centric approach was followed. To alleviate the skew for the modeling, the no precipitation class has been split into 3 classes (dusk/night, sunny, overcast), like in AWD. However, it was still the most occurring class and especially sunny, amounting to over 50% of the total dataset. (And Belgium really isn’t that sunny.) In addition, special cases like tunnels etc. were also added as new classes, and loss has been changed to focal loss, which is known to handle class imbalances better. Class weights were applied to loss during training to tell the model to “pay more attention” to samples from an under-represented class.

With these changes, the new model’s accuracy improved drastically. Not up to the level as on AWD, but this was expected also considering the image quality. Especially precipitation types remained difficult, also as the difference between them are hard to spot, even for humans.

So, what now?

During the SARWS project road trip, we learned and reaffirmed the mantra that good quality data is crucial for ML projects. This also means that the data used for training needs to be representative of the data used in production. Highly-imbalanced data can be a challenge, but there are ways to mitigate it. In any case, we’re happy that WeathercAIm could detect the weather classes with reasonably good accuracy.

Now that we know that AI can see the weather from pictures, what can we do with it? It could be used and applied in all kinds of different industries where having good local weather indication and prediction is crucial like agriculture, sports and recreation, mining, and construction. And in a more general context, combining AI with a camera could be used in many more computer vision tasks as long as you have good-quality data. Feel free to reach out if you want to learn about its opportunities for your project!

In SARWS itself, it was used as one of the sensor inputs for an improved road weather model and a driver app warning drivers about upcoming weather conditions. In the video below you can see all parts of all partners of the SARWS project coming together and how WeathercAIm fits in there.

The post How AI is bridging the gap to safer roads appeared first on Verhaert Masters in Innovation.

The post How AI is bridging the gap to safer roads appeared first on Verhaert Masters in Innovation.

Let’s start by clearing out two main misconceptions about the Robot Operating System (ROS). First of all, it’s not an operating system (OS) and it’s not just useful for robots. But since a ‘Not-Only-For-Robots Not-An-Operating-System’ isn’t quite as catchy, let’s refer to it by its original community-accepted name. Secondly, in this blog we’ll only refer to the robotic mechanical devices and NOT to robotic process automation software.

ROS, what?

What is ROS then? It’s actually a middleware. This means that it’s supposed to be placed between software logic and hardware. It’s similar to a real operating system but needs an operating system platform to run on (usually a Linux distribution). It can’t simply run directly on basic hardware. Moreover, devices need an ROS-specific interface to make use of their power, similar to how operating systems need drivers to access hardware resources.

So if it’s not just for robotics, why does it have ‘robot’ in the name? Because it was developed by the robotics community to be used with robots. Even though it can be used with applications that are not robots, most of the development efforts are directed toward perception, navigation and manipulation tasks. This means that highly complex robotic functionalities are already available in the ROS ecosystem.

ROS, how?

Let’s discuss the core power of ROS: nodes and topics. Nodes are somewhat the atomic pieces of software that implement a desired logic, like retrieving sensor data, capturing images, processing input data or sending input to an actuator. Topics are the communication links between nodes, independent entities that nodes can write or read data from – imagine them as lists of messages like internet chat rooms. These simple mechanisms allow the creation of complex distributed and robust architectures, where the overall system isn’t entirely dependent on the individual. As long as the system design allows it, the entire system is sensor and actuator-agnostic. Imagine a random vacuum cleaner robot: the navigation module doesn’t care if the localization uses lidar, ultrasonic or camera data, or if it’s using wheels, tracks or a propeller to move around.

These components should be easily replaceable, the only necessity is the right ROS node to take the hardware input and offer a standardized output on a specific topic (a driver-like piece of software, as we mentioned before). And here’s another very cool thing: each node can be on a separate computing platform or as many nodes as possible can share the same computing platform at the same time. It’s all up to the application architect to decide. The only prerequisite for ROS is to have a special ‘master’ node running that can be accessed by every other node. The drawback is that if the computing platform running the ‘master node’ disconnects from the system, then the entire system fails.

ROS topology example and in an autonomous car application ©VERHAERT

Above you can find an example of such a topology, as well as applied to a simplified autonomous car application. Keep in mind that each one of these nodes can be on the same or different computer as any of the other nodes. You can even deploy this system on multiple autonomous vehicles and then simply add topics that connect multiple vehicles. The limit of the scalability is set only by the computing or networking resources available.

ROS, why?

‘Standardized’ is another keyword for ROS. Its main goal is to offer a base for true rapid robot prototyping. In 2006, Eric and Keeman decided to create a standard framework for all robots (not yet ROS) when they noticed that in software projects there’s little time left to innovate because most of your time is spent simply making the sensors or actuators work with your system or setting up a communication architecture. The ROS is the successor to their initial framework and it fills the shoes perfectly. No more reinventing the wheel. Once a sensor, actuator or algorithm is successfully interfaced by a developer (or a group), it gets an ROS package made available for everyone to use!

Source: Eric and Keenan pitch deck

We’ve mentioned ‘true rapid prototyping’ before, which might have triggered your spider sense if you’ve spent some time between demonstrators, prototypes and products. Some people tend to oversell the former as the latter, but that’s not the case here. ROS is indeed a prototyping system: it’s not robust enough, doesn’t have real-time capabilities and is easily hackable. Moreover, the master node is required to function at all times.

ROS, next?

ROS2, on the other hand, has a completely different low-level implementation of ROS. It’s still based on nodes and topics, but is far from being a prototyping project and aims to be an industry-ready fully-distributed framework. It has more complex robotic libraries for navigation and manipulation that implement state-of-the-art algorithms and is designed so you can’t develop your packages without abiding by proper software engineering rules. It’s now harder to just create ‘something dirty that works for now’.

Other major changes include the ability to encrypt topics and time synchronization is being handled by the Data Distribution Service, a software framework to reliably and securely communicate in real-time. Furthermore, ROS2 doesn’t have a master node, meaning the application can be entirely distributed across multiple devices without having the inherent critical component. Pretty neat I would say.

Let’s reiterate the key aspects of ROS:

1. Core simplicity
2. Standardization of components
3. Native compatibility with distributed systems
4. Industrial readiness (on the way with ROS2)
5. Available for embedded systems (on the way with ROS2)

It’s clear that ROS is a software to watch. Whether you’re developing a fleet of drones, robot vacuum cleaner, robotic manipulation application, coffee machine or smart beer dispenser, make sure to add this awesome open-source framework in your trade-offs!

Hungry for more? Check out our other blog posts to see how ROS connects hardware with AI!

The post Robotics reinvented: a beginner’s guide to ROS appeared first on Verhaert Masters in Innovation.

The post Robotics reinvented: a beginner’s guide to ROS appeared first on Verhaert Masters in Innovation.

Elevating your Fast Moving Consumer Goods appliances

As technology advances, sensors are becoming more affordable due to improved manufacturing processes and increased competition in the market. This competition has resulted in manufacturers offering sensors in a wide variety to target specific applications. In addition, miniaturization is the first step towards integrating sensors into everyday appliances.

Cost efficiency and size are important, but integrating new sensors can be a challenge. So let’s give you a few examples of the sensing technologies we have employed, their potential applications, and the associated challenges.

1. VIRTUAL TEMPERATURE SENSOR

Temperature is a critical factor to control in appliances, ensuring an accurate and consistent recipe for a quality food or beverage. Temperature sensors are widely used in many applications and are now small and cost-effective. You can use them not only for process monitoring and control but also for signal compensation, as temperature has a considerable influence on most measurements. Despite its widespread usage, there are still challenges that need to be addressed and overcome. Indeed, you can’t indiscriminately add sensors everywhere due to food-safety concerns and/or manufacturing requirements.

For instance, placing a temperature sensor in a beer keg can be difficult. To solve this problem, you can implement virtual temperature sensors, which simulate the behavior of a physical sensor by using data from other physical sensors. Back to the example, the temperature of the contents of a keg can be predicted by using sensors to monitor the temperature of its surroundings. Additionally, you can employ sensor fusion to acquire multiple data and merge the measurements into a single output, ensuring greater reliability and accuracy.

2. SENSITIVE TO PRESSURE?

Beginning with the automotive sector and then extending to numerous industries, pressure sensors are now cost-effective and available in a variety of shapes and sizes. In addition to measuring pressure and flow, you can use these sensors for indirect measurements such as volume. By measuring the pressure and its rate of change over time, it’s possible to calculate the liquid volume contained in a bag.

The post Cost-efficient, compact & insightful: 6 must-have sensors for FMCG appliances appeared first on Verhaert Masters in Innovation.

The post Cost-efficient, compact & insightful: 6 must-have sensors for FMCG appliances appeared first on Verhaert Masters in Innovation.

Complete elimination of ultrafine particles is virtually impossible yet reducing the sources and individual exposure to ultrafine particles within tolerances is the best way to ensure healthy living.
Creating a healthy workplace is critical for cities and mainly for airports to keep operating. Awareness on the topic of ultrafine particles is rising and receives special attention from stakeholders like employees, unions, employers, media, insurance companies, and politics. Providing a healthy work environment is in that respect essential. Yet all sources of ultrafine particles are not identified yet. Where, when, and how much are employees exposed to ultrafine particles is mostly unknown. To start innovating an important question is which (economic) actors have the reason, motivation, and ability to change the existing solutions of ultrafine particles generation and processes where exposure is high? Which (economic) actors are blocking the current adoption of new solutions?

Innovation for effective measures

People working at for example airports face severe health risks. High concentrations of ultrafine particles in combination with long-term exposure cause cardiovascular diseases and have been shown to cause pulmonary inflammation due to the retention in the lungs. Although the effects are highly unknown, research has proved that ultrafine particles translocate to all organs. Long and heavy exposure induces cough, worsens asthma, and is also linked to diabetes and even cancer. The longer people are exposed and the heavier the exposure, the higher the health risk. Research indicates that especially the bay areas and the platforms are subject to high concentrations of ultrafine particles.
We realize that it is hard to imagine for the average worker what the health risks of ultrafine particles are. Ultrafine particles are invisible, and we can’t smell it (yet). Awareness and behavior are critical success factors elements. The behavior of people who work on the airside has a major influence on the exposure to ultrafine particles. Experience has shown that the workforce working on the platform is difficult to mobilize. Think of the limited use of lifting aids in the baggage halls. Explicit attention to behavioral change is mission-critical.

The post When reducing ultrafine particles becomes a matter of health appeared first on Verhaert Masters in Innovation.

The post When reducing ultrafine particles becomes a matter of health appeared first on Verhaert Masters in Innovation.

At Verhaert we are helping our customers to innovate and develop their product portfolio. We have designed and developed more than 1000 products since 1969. Bringing a product to market is not a walk in the park and involves many aspects. One of these aspects is arranging the supply chains delivering the right components at the right time to be able to assemble the electronic boards in your product.

Due to global material and component shortage, specific electronic components can be very hard to come by these days. This situation introduces an extra risk in the product development cycle that must be handled.

The effect of component shortage

Like every other business, we at Verhaert also got affected by the events that happened around us and the rest of the world. Not being able to source desired and necessary components for development can lead to market introduction delays, possibly missing a window of opportunity. In production however, this may very well lead to a complete production stop, with potential customers moving towards your competitors. Multiple examples exist of companies that have products on the market for years, where the production has halted from one day to another, because they cannot source $ 0.3 components. Also the launch of new products is accompanied with a struggle to ramp up the production. Everyone ordering a new (electric) car, or e.g. a PlayStation 5, will know the problem.

It is generally known that the cost of change rises exponentially with the made development progress. It is not worthwhile tackle product risks such as feasibility late in the development process. If you know sooner that a concept can’t work, you will have lost less money on this concept. This means that the size of the changes normally reduces with the progress that you make. This is illustrated in the figure below.

Figure 1: The further the product is in the development, the more difficult it is to change fundamental parts

Now what is the effect of component shortage on this product development process? The component shortage is an unexpected occurrence, striking beyond your control, that forces you to perform such an undesirable design change. This leads you to take a step back in the development cycle, resulting in a higher cost and longer timing, and can even lead to a full stop in production. As component shortage may occur at any moment within the product design phase – and even when the product is on the market – and in any part of your product, this is to be treated as a project risk with a reasonable occurrence rate and a high severity level.

How can we deal with this project risk?

In the process of bringing to and keeping a product on the market, we deal with project risks, and this is no exception to this. How can this (partially) be mitigated? During the previous years, we encountered some component shortage difficulties, and devised some methods to deal with these. The application of each of these possibilities depends on the development phase the product is in and on the envisaged production size. In the remainder of this perspective, these risk mitigation possibilities will be explained, and some practical examples are given for clarification.

1. Risk analysis

The first step when dealing with risks is to make a risk analysis. During the phases where technologies, parts and components are selected, a component shortage risk analysis needs to be made. During this risk analysis, we indicate where there can be a possible problems in lead time and unavailability. This seems to be a lot of work, but this is actually an extension on the exercise to find if there are multiple suppliers for the same component.

How do we tackle this in practice? We perform a risk analysis to find multiple suppliers and add the regular lead time to the equation. For components where we see little alternatives, and with large lead times, it may be better to change this circuit. During the initial development phases it is the ‘easiest’ to change the implementation. The further in the development process, the more difficult this becomes.

It often happens that some parts seem ideal for the specific needs of a product. This also was the case in one of our projects. The lead time was more than one year however. This was the reason why alternatives were found and adjustments were made in the production prototype phase. This resulted in a more robust circuit from component shortage point-of-view.

The post 7 methods to deal with component shortage appeared first on Verhaert Masters in Innovation.

The post 7 methods to deal with component shortage appeared first on Verhaert Masters in Innovation.

Measuring data without sensors

Virtual sensors allow you to measure data, without the traditional physical components. In its simplest definition, a virtual sensor can be translated into the software version of a sensor device. In a more extended definition, a virtual sensor imitates the tasks of a physical sensor at the software level and thus provides multiple services to its users at the node, network or application level of the cloud.

But then again, replacing all physical sensors by virtual counterparts would be quite impossible. You’ll always need a hardware component to access the data. The real gain can be found in selecting your physical sensors wisely and enriching it with smart algorithms to support multiple applications simultaneously.

A good example of a virtual sensor can be found in today’s CO2 sensors. In post-pandemic times, it’s almost impossible to imagine classrooms, hospitals and meeting rooms without one. However, did you know that quite a substantial amount of CO2 measuring devices is not directly measuring CO2? More often than not, the onboard sensor detects a range of different gasses. It’s an algorithm that calculates the approximate presence of CO2.

As a consequence, IoT solution providers have been looking for ways to combine less accurate (read: cheaper) sensors to achieve a good enough software solution (compared to the higher-end physical sensors). Through a smart design, you get a similar outcome, but at a lower production cost.

Reducing pricing & physical components

It’s therefore important to take a step back as soon as you start designing a system architecture and think about the business requirements of your solution. Pricing is an essential part of your product strategy and simply adding expensive components must also pass the viability test compared to other products. The question that product owners should therefore ask themselves is to what extent the newly added sensor actually adds value to the proposition.

The post How to outsmart the component shortage of sensor ICs appeared first on Verhaert Masters in Innovation.

The post How to outsmart the component shortage of sensor ICs appeared first on Verhaert Masters in Innovation.

Current road weather prediction models using car sensor data

Studies show that lower visibility or slippery surfaces because of rain or snow make driving more difficult and result in more traffic accidents. Dedicated road weather models (RWM’s) have long been a useful tool to forecast poor road conditions. However, these RWM’s typically depend on fixed observation stations that don’t cover the entire road network. Let’s take a first step to improve road weather models and road services by using vehicle sensor observations.

Well-known reactive systems such as stability control and anti-lock brakes are already standard options on cars, because they’re vital for driver safety. However, these advanced driver assistance systems only activate when they detect danger. Proactive real-time safety warnings could prevent the situation altogether by alerting the driver. Other than that, road weather data could also help authorities to adapt road management more accurately.

Fortunately, there’s already a rise in connected vehicles and their sensing capabilities. The connected car market was worth $13 billion in 2012, more than doubled by 2019 ($42.6 billion) and is expected to be worth $212.7 billion by 2027. Utilizing the sensing capabilities of this new generation of connected vehicles could create a dense observation network for real-time local road weather warnings, and even improve weather prediction models.

Real-time warnings for dangerous road conditions

Verhaert, along with other industrial stakeholders and researchers from 7 countries (Belgium, France, Portugal, Romania, Spain, Turkey, and South Korea) initiated the SARWS project to provide real-time weather services, wanting to expand the local data collection mechanisms from traditional data sources towards large-scale vehicle fleets.

Our technology aims to use crowd-sourced car sensor data for real-time road weather warnings for local weather phenomena and dangerous road conditions. Moreover, these observations enhance the RMI road weather model and validate a fog product based on a weather model.

The primarily targeted weather conditions in the SARWS project are air and road surface temperature, visibility and road surface conditions. This could still be extended with precipitation and crosswinds. We gather local measurements from a fleet provided by a Belgian post service. The collected data is then used for:

• Analyzing time-series to detect weather- related information,
• Enhancing road weather models developed at RMI,
• Providing real-time weather services to warn drivers and authorities.

The post Car sensor data improving road weather services appeared first on Verhaert Masters in Innovation.

The post Car sensor data improving road weather services appeared first on Verhaert Masters in Innovation.

You can see a clear trend of moving from corded to cordless devices in product development. Creating battery-powered devices can be a challenge because of high-current drain and high-battery discharge cycles. In this webinar, Jan Buytaert Consultant PhysicsLab at Verhaert, discusses the successful development of an example device that is on the limit of the current battery technology, focusing on the development and testing strategy.

Watch the recording

View the presentation

 

The post High-current battery-powered handheld devices appeared first on Verhaert Masters in Innovation.

The post High-current battery-powered handheld devices appeared first on Verhaert Masters in Innovation.